regrank 0.2.30

Regularized methods for efficient ranking in networks

regrank implements a collection of regularized, convex models (+solvers) that allow the inference of hierarchical structure in a directed network, which exists due to dominance, social status, or prestige. Specifically, this work leverages the time-varying structure and/or the node metadata present in the data set.

This is the software repository behind the paper:

• Tzu-Chi Yen and Stephen Becker, Regularized methods for efficient ranking in networks, in preparation.
• For full documentation, please visit this site.
• General Q&A, ideas, or other things, please visit Discussions.
• Software-related bugs, issues, or suggestions, please use Issues.

Installation

regrank is available on PyPI. It also depends on graph-tool. We recommend using conda to manage packages.

conda create --name regrank-dev -c conda-forge graph-tool
conda activate regrank-dev
pip install regrank

Example

# Import the library
import regrank as rr

# Load a data set
g = rr.datasets.us_air_traffic()

# Create a model
model = rr.optimize.regrank(method="annotated")

# Fit the model: We decided to analyze the `state_abr` nodal metadata,
# We may inspect `g.list_properties()` for other metadata to analyze.
result = model.fit(g, alpha=1, lambd=0.5, goi="state_abr")

# Now, result["primal"] should have the rankings. We can compute a summary.
summary = rr.compute_summary(g, "state_abr", primal_s=result["primal"])

Let's plot the rankings, via rr.plot_hist(summary). Note that most of the node categories are regularized to have the same mean ranking.

We provided a summary via rr.print_summary_table(summary).

  +-------+-------+--------+-----------------------------------------+--------+---------+
  | Group | #Tags | #Nodes | Members                                 |   Mean |     Std |
  +-------+-------+--------+-----------------------------------------+--------+---------+
  | 1     |     5 |    825 | CA, WA, OR, TT, AK                      |  0.047 | 1.1e-02 |
  | 2     |     4 |    206 | TX, MT, PA, ID                          | -0.006 | 4.2e-03 |
  | 3     |    43 |   1243 | MI, IN, TN, NC, VA, IL, CO, WV, MA, WI, | -0.035 | 4.3e-03 |
  |       |       |        | SC, KY, MO, MD, AZ, PR, LA, UT, MN, GA, |        |         |
  |       |       |        | MS, HI, DE, NM, ME, NJ, NE, VT, CT, SD, |        |         |
  |       |       |        | IA, NV, ND, AL, OK, AR, NH, RI, OH, FL, |        |         |
  |       |       |        | KS, NY, WY                              |        |         |
  | 4     |     1 |      4 | VI                                      | -0.072 | 0.0e+00 |
  +-------+-------+--------+-----------------------------------------+--------+---------+

The result suggests that states such as CA, WA, or AK are significantly more popular than other states.

Data sets

We have a companion repo—regrank-data—for data sets used in the paper. Which are:

• PhD_exchange
• Parakeet

In addendum, we have provided the regrank.datasets submodule to load data sets hosted by other repositories, such as the Netzschleuder. See the docs for more information.

Development

The library uses pytest to ensure correctness. The test suite depends on mosek and gurobi.

License

regrank is open-source and licensed under the GNU Lesser General Public License v3.0.